SwitchTab: Switched Autoencoders Are Effective Tabular Learners

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wu, Jing, Chen, Suiyao, Zhao, Qi, Sergazinov, Renat, Li, Chen, Liu, Shengjie, Zhao, Chongchao, Xie, Tianpei, Guo, Hanqing, Ji, Cheng, Cociorva, Daniel, Brunzel, Hakan
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913185329577984
author Wu, Jing
Chen, Suiyao
Zhao, Qi
Sergazinov, Renat
Li, Chen
Liu, Shengjie
Zhao, Chongchao
Xie, Tianpei
Guo, Hanqing
Ji, Cheng
Cociorva, Daniel
Brunzel, Hakan
author_facet Wu, Jing
Chen, Suiyao
Zhao, Qi
Sergazinov, Renat
Li, Chen
Liu, Shengjie
Zhao, Chongchao
Xie, Tianpei
Guo, Hanqing
Ji, Cheng
Cociorva, Daniel
Brunzel, Hakan
contents Self-supervised representation learning methods have achieved significant success in computer vision and natural language processing, where data samples exhibit explicit spatial or semantic dependencies. However, applying these methods to tabular data is challenging due to the less pronounced dependencies among data samples. In this paper, we address this limitation by introducing SwitchTab, a novel self-supervised method specifically designed to capture latent dependencies in tabular data. SwitchTab leverages an asymmetric encoder-decoder framework to decouple mutual and salient features among data pairs, resulting in more representative embeddings. These embeddings, in turn, contribute to better decision boundaries and lead to improved results in downstream tasks. To validate the effectiveness of SwitchTab, we conduct extensive experiments across various domains involving tabular data. The results showcase superior performance in end-to-end prediction tasks with fine-tuning. Moreover, we demonstrate that pre-trained salient embeddings can be utilized as plug-and-play features to enhance the performance of various traditional classification methods (e.g., Logistic Regression, XGBoost, etc.). Lastly, we highlight the capability of SwitchTab to create explainable representations through visualization of decoupled mutual and salient features in the latent space.
format Preprint
id arxiv_https___arxiv_org_abs_2401_02013
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SwitchTab: Switched Autoencoders Are Effective Tabular Learners
Wu, Jing
Chen, Suiyao
Zhao, Qi
Sergazinov, Renat
Li, Chen
Liu, Shengjie
Zhao, Chongchao
Xie, Tianpei
Guo, Hanqing
Ji, Cheng
Cociorva, Daniel
Brunzel, Hakan
Machine Learning
Self-supervised representation learning methods have achieved significant success in computer vision and natural language processing, where data samples exhibit explicit spatial or semantic dependencies. However, applying these methods to tabular data is challenging due to the less pronounced dependencies among data samples. In this paper, we address this limitation by introducing SwitchTab, a novel self-supervised method specifically designed to capture latent dependencies in tabular data. SwitchTab leverages an asymmetric encoder-decoder framework to decouple mutual and salient features among data pairs, resulting in more representative embeddings. These embeddings, in turn, contribute to better decision boundaries and lead to improved results in downstream tasks. To validate the effectiveness of SwitchTab, we conduct extensive experiments across various domains involving tabular data. The results showcase superior performance in end-to-end prediction tasks with fine-tuning. Moreover, we demonstrate that pre-trained salient embeddings can be utilized as plug-and-play features to enhance the performance of various traditional classification methods (e.g., Logistic Regression, XGBoost, etc.). Lastly, we highlight the capability of SwitchTab to create explainable representations through visualization of decoupled mutual and salient features in the latent space.
title SwitchTab: Switched Autoencoders Are Effective Tabular Learners
topic Machine Learning
url https://arxiv.org/abs/2401.02013